Medicine
Permanent URI for this communityhttp://repository.kln.ac.lk/handle/123456789/12
This repository contains the published and unpublished research of the Faculty of Medicine by the staff members of the faculty
Browse
7 results
Search Results
Item Pilot study for non-invasive diabetes detection through classification of photoplethysmography signals using convolutional neural networks(University of Kelaniya, 2024) Gunathilaka, H.J.; Rajapaksha, R.; Kumarika, T.; Perera, D.; Herath, U.; Jayathilaka, C.; Liyanage, J.A.; Kalingamudali, S.R.D.Diabetes is a chronic disorder affecting vascular health, often altering pulse wave characteristics. Traditional pulse wave analysis (PWA) methods face challenges such as variability and complexity of signals. This study aims to overcome these limitations by leveraging deep learning models for more accurate and efficient classification. The methodology used in this study involves four key steps: data collection, data preprocessing, Convolutional Neural Network (CNN) model development, and model evaluation. Primary data were collected using a multipara patient monitor, including finger photoplethysmography (PPG) signals, blood pressure, mean arterial pressure, oxygen saturation, and pulse rate. Single pulse wave cycles from 60 healthy individuals and 60 patients with type 2 diabetes underwent preprocessing. The CNN model was trained using 50 PPG images from each group and achieved a training accuracy of 92%. The prediction capability of the model was evaluated using 20 unseen images, comprising 10 healthy and 10 diabetes PPG images. It attained a 90% overall test accuracy in distinguishing between PPG images of individuals with diabetes and those who are healthy. These findings suggest that CNNbased analysis of PPG signals provides a precise, non-invasive tool for diabetes screening. To further enhance accuracy, future studies should focus on increasing the dataset size and performing hyperparameter tuning to optimize the CNN model.Item Non-invasive diagnostic approach for diabetes using pulse wave analysis and deep learning(MDPI, 2024) Gunathilaka, H.; Rajapaksha, R.; Kumarika, T.; Perera, D.; Herath, U.; Jayathilaka, C.; Liyanage, J.; Kalingamudali, S.The surging prevalence of diabetes globally necessitates advancements in non-invasive diagnostics, particularly for the early detection of cardiovascular anomalies associated with the condition. This study explores the efficacy of Pulse Wave Analysis (PWA) for distinguishing diabetic from non-diabetic individuals through morphological examination of pressure pulse waveforms. The research unfolds in four phases: data accrual, preprocessing, Convolutional Neural Network (CNN) model construction, and performance evaluation. Data were procured using a multipara patient monitor, resulting in 2000 pulse waves equally divided between healthy individuals and those with diabetes. These were used to train, validate, and test three distinct CNN architectures: the conventional CNN, Visual Geometry Group (VGG16), and Residual Networks (ResNet18). The accuracy, precision, recall, and F1 score gauged each model’s proficiency. The CNN demonstrated a training accuracy of 82.09% and a testing accuracy of 80.6%. The VGG16, with its deeper structure, surpassed the baseline with training and testing accuracies of 90.2% and 86.57%, respectively. ResNet18 excelled, achieving a training accuracy of 92.50% and a testing accuracy of 92.00%, indicating its robustness in pattern recognition within pulse wave data. Deploying deep learning for diabetes screening marks progress, suggesting clinical use and future studies on bigger datasets for refinement.Item Domain-Specific learning among medical students(Basic Medical Scientists Association, 2012) Perera, D.; Ramanayake, R.P.J.C.; de Silva, A.H.W.; Sumanasekara, R.D.N.; Jayasinghe, L.R.; Gunasekara, R.; Chandrasiri, P.Background: The aim of this study was to investigate undergraduate medical student’s domain-specific learning. Method: The research tool was a structured essay question formulated to assess factual and affective knowledge and application and synthesis of knowledge .The question was administered to 151 students. Results: Mean score on the recall question was significantly higher than the other two domains. Total scores of female students were significantly higher than male students (P<0.05). Gender-wise difference in scores was not significant in any specific domain area. There was no significant relationship between factual knowledge and total scores. However, there was a significant linear relationship between total scores and the two areas of affective knowledge (r=0.78) and application and synthesis of knowledge (r=0.6). Findings indicate that affective knowledge and application of knowledge are closely related to overall acquisition of knowledge (P<0.0005). Conclusion: Teaching and assessment in higher-order knowledge domains and affective knowledge needs to be developed. Questions dealing with affective knowledge and testing higher-order cognitive abilities are more discriminatory than questions testing at the recall level.Item A Comparative analysis of the outcome of malaria case surveillance strategies in Sri Lanka in the prevention of re-establishment phase(BioMed Central, 2021) Gunasekera, W.M.K.T.A.W.; Premaratne, R.; Fernando, D.; Munaz, M.; Piyasena, M.G.Y.; Perera, D.; Wickremasinghe, R.; Ranaweera, K.D.N.P.; Mendis, K.BACKGROUND: Sri Lanka sustained its malaria-free status by implementing, among other interventions, three core case detection strategies namely Passive Case Detection (PCD), Reactive Case Detection (RACD) and Proactive Case Detection (PACD). The outcomes of these strategies were analysed in terms of their effectiveness in detecting malaria infections for the period from 2017 to 2019. METHODS: Comparisons were made between the surveillance methods and between years, based on data obtained from the national malaria database and individual case reports of malaria patients. The number of blood smears examined microscopically was used as the measure of the volume of tests conducted. The yield from each case detection method was calculated as the proportion of blood smears which were positive for malaria. Within RACD and PACD, the yield of sub categories of travel cohorts and spatial cohorts was ascertained for 2019. RESULTS: A total of 158 malaria cases were reported in 2017-2019. During this period between 666,325 and 725,149 blood smears were examined annually. PCD detected 95.6 %, with a yield of 16.1 cases per 100,000 blood smears examined. RACD and PACD produced a yield of 11.2 and 0.3, respectively. The yield of screening the sub category of travel cohorts was very high for RACD and PACD being 806.5 and 44.9 malaria cases per 100,000 smears, respectively. Despite over half of the blood smears examined being obtained by screening spatial cohorts within RACD and PACD, the yield of both was zero over all three years. CONCLUSIONS: The PCD arm of case surveillance is the most effective and, therefore, has to continue and be further strengthened as the mainstay of malaria surveillance. Focus on travel cohorts within RACD and PACD should be even greater. Screening of spatial cohorts, on a routine basis and solely because people are resident in previously malarious areas, may be wasteful, except in situations where the risk of local transmission is very high, or is imminent. These findings may apply more broadly to most countries in the post-elimination phase. KEYWORDS: Active case detection; Malaria case surveillance; Malaria in Sri Lanka; Passive case detection; Prevention of re-establishment of malaria; Proactive case detection; Reactive case detection; Spatial cohorts; Travel cohorts; Yield.Item Case report: Opportunities for Medication Review and Reconciliation by a Clinical Pharmacist to Prevent Drug-Related Hospital Re-Admissions: Evidence from a Case Series in Sri Lanka(Pharmaceutical Journal of Sri Lanka, 2018) Shanika, L.G.T.; Wijekoon, C.N.; Jayamanne, S.; Coombes, J.; Perera, D.; Pathiraja, V.M.; Mamunuwa, N.; Mohamed, F.; Coombes, I.; Lynch, C.; de Silva, H.A.; Dawson, A.H.ABSTRACT: Medication review by a clinical pharmacist improves quality use of medicines in patients by identifying, reducing and preventing drug related problems and hospital re-admissions. This service is new to Sri Lanka. We present two cases from a non-randomized controlled trial conducted in a tertiary care hospital in Sri Lanka. The first case is from the control group where no clinical pharmacist was engaged and the next case is from the intervention group. The first case was a drug related hospital re-admission because of missing medicines in the discharge prescription and the second case was a re-admission which was prevented by the intervention of a ward pharmacist by performing a clinical medication review of the prescription.Item Road rage in Sri Lanka: prevalence and psychiatric distress(Sri Lanka Medical Association, 2015) Rodrigo, A.; Perera, D.; Eranga, V.P.; Peris, M.U.P.K.; Pathmeswaran, A.INTRODUCTION: Road traffic accidents are a major public health concern in Sri Lanka. Aggressive and reckless driving is an important contributor to the high rate of road traffic accidents. OBJECTIVE: We studied prevalence, nature, determinants and associated psychiatric morbidity ofroad rage among motorists in Sri Lanka. Methods Data were gathered from 238 randomly selected motorists in Sri Lanka using a modified questionnaire regarding road rage and the 6-item version of Kessler's psychological distress scale. RESULTS: While 98.7% participants reported being victims of road rage, 85.3% were involved in offending behaviour. However actual physical assault (0.8%) and damage to vehicles (2.5%) were rare. Male gender, young age, increased traffic density and driving a three-wheeler or bus were associated with daily road rage victimisation and perpetration. Psychiatric distress was associated with being a victim of road rage. CONCLUSIONS: High prevalence of road rage in Sri Lanka and significant psychiatric distressassociated with it indicate the necessity of interventions at least for target groupsItem The Knowledge and attitude of primary school teachers in Sri Lanka towards childhood attention deficit hyperactivity disorder(Sri Lanka Medical Association, 2011) Rodrigo, M.D.A.; Perera, D.; Eranga, V.P.; Williams, S.S.; Kuruppuarachchi, K.A.L.A.OBJECTIVE: To assess the knowledge and attitudes towards attention deficit hyperactivity disorder (ADHD) among primary school teachers in the Gampaha District. METHODS: A descriptive cross sectional study was conducted in randomly selected schools of Gampaha district using a stratified sampling method. The knowledge and attitudes on ADHD were assessed by a self-administered questionnaire distributed among all the consenting primary school teachers in the selected schools. RESULTS: Total of 202 completed questionnaires of 210 distributed were returned. The majority showed good understanding about ill effects of ADHD, teachers' role in management and counterproductive effects of punishment. Three-fourths had a positive attitude towards behavioural therapy. However, only a minority had adequate knowledge about the presentation of ADHD and its treatment with medication. More than 80% of teachers believed that the parents were to be blamed for the child's ADHD. The majority of participating teachers also believed that behavioural disturbances caused by ADHD children were deliberate and malicious. Teachers who had training in child psychology recorded a significantly higher knowledge and had a more favourable attitude. CONCLUSIONS: The knowledge of ADHD and its treatment among primary school teachers needs to be improved. Particular focus should be on improving attitudes and disseminating the message that timely interventions can make a difference in the educational and social development of the child.